Initialize paths

knitr::opts_chunk$set(echo = TRUE)


setwd("/restricted/projectnb/llfs/LinGA_protected/analysis/genomics/metabolomics/paola_analysis/age_change/")
dir() 
##  [1] "2023.01.18.llfs.metab.age.change.csv"                           
##  [2] "2023.03.31.llfs.metab.age.change.csv"                           
##  [3] "2024.06.14.llfs.metab.age.change.csv"                           
##  [4] "2024.06.22.llfs.metab.age.change.csv"                           
##  [5] "Age_rel.change.assoc_batch4.pc_gee.06.14.2024.csv"              
##  [6] "Age_rel.change.assoc_batch4.pc_gee.06.22.2024.csv"              
##  [7] "Age_rel.change.assoc_batch4.pc_genesis.03.31.2023.csv"          
##  [8] "Age_rel.change.assoc_batch5.pc_gee.06.14.2024.csv"              
##  [9] "Age_rel.change.assoc_batch5.pc_gee.06.22.2024.csv"              
## [10] "Age_rel.change.assoc_batch5.pc_genesis.03.31.2023.csv"          
## [11] "Metabolite.batch4_age_relative.change_assoc_03.31.2023.Rmd"     
## [12] "Metabolite.batch4_age_relative.change_assoc_03.31.2023.html"    
## [13] "Metabolite.batch4_age_relative.change_gee.06.14.2024.Rmd"       
## [14] "Metabolite.batch4_age_relative.change_gee.06.14.2024.html"      
## [15] "Metabolite.batch5_age_relative.change_assoc_03.31.2023.Rmd"     
## [16] "Metabolite.batch5_age_relative.change_assoc_03.31.2023.html"    
## [17] "Metabolite.batch5_age_relative.change_gee.06.14.2024.Rmd"       
## [18] "Metabolite.batch5_age_relative.change_gee.06.14.2024.html"      
## [19] "aggregate_res.html"                                             
## [20] "aggregate_res.rmd"                                              
## [21] "analysis.final.no.missing.dat.batch4.csv"                       
## [22] "analysis.final.no.missing.dat.batch5.csv"                       
## [23] "annotated_Age_rel.change_assoc_batch4.pc_gee.06.14.2024.csv"    
## [24] "annotated_Age_rel.change_assoc_batch4.pc_gee.06.22.2024.csv"    
## [25] "annotated_Age_rel.change_assoc_batch4.pc_genesis.03.31.2023.csv"
## [26] "annotated_Age_rel.change_assoc_batch5.pc_gee.06.14.2024.csv"    
## [27] "annotated_Age_rel.change_assoc_batch5.pc_gee.06.22.2024.csv"    
## [28] "annotated_Age_rel.change_assoc_batch5.pc_genesis.03.31.2023.csv"
## [29] "archived"                                                       
## [30] "plot_dir"                                                       
## [31] "results"                                                        
## [32] "run.all.o47338"                                                 
## [33] "run.all.o47360"                                                 
## [34] "run.all.o47616"                                                 
## [35] "run.all.o47619"                                                 
## [36] "run.all.o6731500"                                               
## [37] "run.all.o6731805"                                               
## [38] "run.all.o6731810"                                               
## [39] "run.all.o6745611"                                               
## [40] "run.all.o8069748"                                               
## [41] "run.all.o8071790"                                               
## [42] "run.all.o8072902"                                               
## [43] "run.all.o8073016"                                               
## [44] "run.all.o8073512"                                               
## [45] "run.all.o8074280"                                               
## [46] "run.all.o8074309"                                               
## [47] "run.all.o8084021"                                               
## [48] "run.all.o8084022"                                               
## [49] "run.all.o8084112"                                               
## [50] "run.all.o8084129"                                               
## [51] "run.all.o8084254"                                               
## [52] "run.all.o8084454"                                               
## [53] "run.all.o8214887"                                               
## [54] "run.all.o8214986"                                               
## [55] "run.all.o8214997"                                               
## [56] "run.all.o8215010"                                               
## [57] "run.all.o8215103"                                               
## [58] "run.all.o8215105"                                               
## [59] "run.all.o8216530"                                               
## [60] "run.all.o8216740"                                               
## [61] "run.all.o8222441"                                               
## [62] "run.batch4.2.qsub"                                              
## [63] "run.batch4.qsub"                                                
## [64] "run.batch5.2.qsub"                                              
## [65] "run.batch5.qsub"                                                
## [66] "run_aggregate.sub"
llfs.pheno.dir <- "/restricted/projectnb/llfs/LinGA_protected/analysis/genomics/metabolomics/paola_analysis/generate_list_metabolomics/"
llfs.metab4.dir <- "/restricted/projectnb/llfs/LLFS_omics/LLFS_metabolomics/batch4_20220506/"
llfs.metab3.dir <- "/restricted/projectnb/llfs/LLFS_omics/LLFS_metabolomics/batch3_20220325/"
llfs.metab5.dir <- "/restricted/projectnb/llfs/LLFS_omics/LLFS_metabolomics/batch5_20221220/"
annot.dir <- "/restricted/projectnb/necs/Data_library/Metabolomics/NECS/metabolic_data/annotation/"
library(readxl)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(ggplot2)
library(Heatplus)
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.2 --
## v tibble  3.1.7     v purrr   0.3.4
## v tidyr   1.2.0     v stringr 1.4.0
## v readr   2.1.2     v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(coxme)
## Loading required package: survival
## Loading required package: bdsmatrix
## 
## Attaching package: 'bdsmatrix'
## 
## The following object is masked from 'package:base':
## 
##     backsolve
library(GENESIS)
suppressPackageStartupMessages(library(SeqArray))
suppressPackageStartupMessages(library(SeqVarTools))
library(Biobase)
## Loading required package: BiocGenerics
## 
## Attaching package: 'BiocGenerics'
## 
## The following objects are masked from 'package:dplyr':
## 
##     combine, intersect, setdiff, union
## 
## The following objects are masked from 'package:stats':
## 
##     IQR, mad, sd, var, xtabs
## 
## The following objects are masked from 'package:base':
## 
##     Filter, Find, Map, Position, Reduce, anyDuplicated, append,
##     as.data.frame, basename, cbind, colnames, dirname, do.call,
##     duplicated, eval, evalq, get, grep, grepl, intersect, is.unsorted,
##     lapply, mapply, match, mget, order, paste, pmax, pmax.int, pmin,
##     pmin.int, rank, rbind, rownames, sapply, setdiff, sort, table,
##     tapply, union, unique, unsplit, which.max, which.min
## 
## Welcome to Bioconductor
## 
##     Vignettes contain introductory material; view with
##     'browseVignettes()'. To cite Bioconductor, see
##     'citation("Biobase")', and for packages 'citation("pkgname")'.
library(lubridate)
## 
## Attaching package: 'lubridate'
## 
## The following objects are masked from 'package:BiocGenerics':
## 
##     intersect, setdiff, union
## 
## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union
library(geepack)

Read data and basic QC

Read LLFS list forbatch 4

use fake names of metabolites for analysis and annotate at the end

use data in the long format and analyze using GEE

llfs.data.batch5 <- read.csv(paste0(llfs.pheno.dir,  "llfs.data.metabolom.batch5.change.03.31.2023.csv"), 
                             header=T, na.strings = c("", NA), check.names=F) %>%
       # generate age at blood.2
  mutate(Age.blood.2 = year(dmy(date.blood))-BirthYear) %>% 
  mutate( delta.t = Age.blood.2-Age.e) 

   dim(llfs.data.batch5)
## [1] 3898   20
  met.5.llfs <- readr::read_csv(paste0(llfs.metab5.dir, "peak_areas_pos_neg_merged_imputed_normalized.20221220.csv")) %>%
    mutate( fake.subject = paste(subject, visitcode, sep="_"), .after = visitcode) 
## Rows: 3937 Columns: 222
## -- Column specification --------------------------------------------------------
## Delimiter: ","
## dbl (222): subject, visitcode, DL-2-Aminooctanoic acid, Homostachydrine, 2-A...
## 
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.
    n.metab <- ncol(met.5.llfs)-3
     orig.metab.names <- names(met.5.llfs)[4:ncol(met.5.llfs)]
     fake.metab.names <- paste0("metab", c(1:n.metab))
     metab.look.up.table <- data.frame( orig.metab.names, fake.metab.names)
     names(met.5.llfs)[4:ncol(met.5.llfs)] <- fake.metab.names

Data formatting–

met.llfs <- met.5.llfs
dim(met.llfs)
## [1] 3937  223
 table(met.llfs$visitcode)
## 
##    1    3    4 
## 2686 1246    5
# extract patients data at visiti 1 or enrolled at visit 2
 met.llfs.vst1 <- met.llfs %>%
  filter(visitcode==1 | visitcode==4)
met.data.1 <- as.data.frame(t(met.llfs.vst1[ , 4:ncol(met.llfs.vst1)]))
dim(met.data.1)
## [1]  220 2691
colnames(met.data.1) <- met.llfs.vst1$subject

# extract patients data at visit2  
met.llfs.vst2 <- met.llfs %>%
  filter(visitcode==3)
met.data.2 <- as.data.frame(t(met.llfs.vst2[ , 4:ncol(met.llfs.vst2)]))
dim(met.data.2)
## [1]  220 1246
colnames(met.data.2) <- met.llfs.vst2$subject

common.id <- intersect(met.llfs.vst1$subject, met.llfs.vst2$subject)
common.metab <- intersect(row.names(met.data.1), row.names(met.data.2)) 
  length(common.id)
## [1] 1207
  length(common.metab)
## [1] 220
 ## Generate data with visit 1 and 2 metabolomic data
    met.data.1 <- as.data.frame(met.data.1[ match(common.metab, row.names(met.data.1)), match(as.character(common.id), names(met.data.1) )])
     names(met.data.1) <- paste0(names(met.data.1), "_1")
    met.data.2 <- as.data.frame(met.data.2[ match(common.metab, row.names(met.data.2)), match(as.character(common.id), names(met.data.2) )])
     names(met.data.2) <- paste0(names(met.data.2), "_3")
     
     met.data <- cbind(met.data.1, met.data.2)

Data visualization and outlier detection in met.data.1

met.data.1 <- met.data
hist(apply(met.data.1,2,min))

summary(apply(met.data.1,2,min))
##     Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
##     5.66  2695.45  4902.19  5249.32  7160.51 46605.56
boxplot((met.data.1))

pca.res <- prcomp(log(t(met.data.1)), scale. = T)
 # summary(pca.res)
    plot(pca.res$x[,1:2])

      outliers <- names(which(pca.res$x[,1] < -20))
      ok.samples <- setdiff(names(met.data.1), outliers)
  new.met.data.1 <- met.data.1[ , as.character(ok.samples)]

  pca.res <- prcomp(log(t(new.met.data.1)), scale. = T)
   ## summary(pca.res)
    plot(pca.res$x[,1:2])

   # filter out bad samples  
     met.data.1 <- data.frame(fake.subject = ok.samples, t(met.data.1[ , ok.samples]))
   dim(met.data.1)
## [1] 2413  221
      # now drop outliers
      n.outlier <- c()
  for(ind.col in 2:ncol(met.data.1)){
          this.metab <- log(met.data.1[,ind.col])
           this.mean <- mean(this.metab, na.rm=T)
           this.var  <- var(this.metab, na.rm=T)
              set.to.na <- which((this.metab > this.mean+4*sqrt(this.var)) | 
                               (this.metab < this.mean-4*sqrt(this.var)))
              met.data.1[set.to.na, ind.col ] <-  exp(this.mean)
              n.outlier <- c(n.outlier, length(set.to.na))
    }
    summary(n.outlier)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   0.000   1.000   4.000   7.018   8.000  88.000
    hist(n.outlier)

# Order by ID  
    met.data.1 <- met.data.1[order(met.data.1$fake.subject),]

generate analysis data set

 analysis.master.dat <- met.data.1 %>%
    left_join( llfs.data.batch5, by = c("fake.subject"))
           dim(analysis.master.dat)
## [1] 2413  240
  ## correct delta age for long format analysis
           analysis.master.dat$delta.t[analysis.master.dat$visitcode == 1] <- 0

pca and grm

pc.df <- read.csv("/rprojectnb2/llfs/LinGA_protected/analysis/genetics/GWAS_EL_Zeyuan/LLFS_PCA_GRM/llfs_pcair.csv")
analysis.dat <- left_join(analysis.master.dat, pc.df, by=c("subject"="sample.id"))

#png("PC1vsPC2_4577.png")
ggplot(analysis.dat, aes(PC1, PC2)) + geom_point()
## Warning: Removed 114 rows containing missing values or values outside the scale range
## (`geom_point()`).

#dev.off()

#png("PC3vsPC4_4577.png")
ggplot(analysis.dat, aes(PC3, PC4)) + geom_point()
## Warning: Removed 114 rows containing missing values or values outside the scale range
## (`geom_point()`).

#dev.off()

#PCA plots look good
#80 with missing PCs

association

library(gee)
 analysis.final.dat <- analysis.dat %>%
   mutate(FC_DK = FC == "DK") %>%
   select( row.names(met.data), fake.subject, subject, visitcode,
            Age.e, delta.t, Sex, Education, FC_DK, PC1, PC2, PC3, PC4,
         htn_meds, lipid_meds, nitro_meds, t2d_meds)
dim(analysis.final.dat)
## [1] 2413  236
#1717

var.list <- c("Age.e", "delta.t",
              "Education","Sex","FC_DK","PC1","PC2","PC3","PC4","htn_meds","lipid_meds","nitro_meds","t2d_meds")
summary(analysis.final.dat[,var.list])
##      Age.e          delta.t         Education         Sex           
##  Min.   : 36.0   Min.   : 0.000   Min.   : 2.00   Length:2413       
##  1st Qu.: 56.0   1st Qu.: 0.000   1st Qu.:10.00   Class :character  
##  Median : 63.0   Median : 5.000   Median :14.00   Mode  :character  
##  Mean   : 65.8   Mean   : 4.236   Mean   :12.69                     
##  3rd Qu.: 73.0   3rd Qu.: 8.000   3rd Qu.:15.00                     
##  Max.   :102.0   Max.   :12.000   Max.   :17.00                     
##                                   NA's   :4                         
##    FC_DK              PC1                PC2                PC3          
##  Mode :logical   Min.   :-0.02359   Min.   :-0.08599   Min.   :-0.12233  
##  FALSE:2104      1st Qu.:-0.01226   1st Qu.:-0.01010   1st Qu.:-0.00196  
##  TRUE :309       Median :-0.00796   Median :-0.00323   Median : 0.00289  
##                  Mean   : 0.00169   Mean   :-0.00436   Mean   :-0.00061  
##                  3rd Qu.: 0.00903   3rd Qu.: 0.00683   3rd Qu.: 0.00809  
##                  Max.   : 0.07540   Max.   : 0.07442   Max.   : 0.04129  
##                  NA's   :114        NA's   :114        NA's   :114       
##       PC4              htn_meds        lipid_meds       nitro_meds    
##  Min.   :-0.05021   Min.   :0.0000   Min.   :0.0000   Min.   :0.0000  
##  1st Qu.:-0.00702   1st Qu.:0.0000   1st Qu.:0.0000   1st Qu.:0.0000  
##  Median : 0.00431   Median :0.0000   Median :0.0000   Median :0.0000  
##  Mean   : 0.00413   Mean   :0.4557   Mean   :0.3715   Mean   :0.2358  
##  3rd Qu.: 0.01324   3rd Qu.:1.0000   3rd Qu.:1.0000   3rd Qu.:0.0000  
##  Max.   : 0.09302   Max.   :1.0000   Max.   :1.0000   Max.   :1.0000  
##  NA's   :114        NA's   :157      NA's   :157      NA's   :157     
##     t2d_meds      
##  Min.   :0.00000  
##  1st Qu.:0.00000  
##  Median :0.00000  
##  Mean   :0.06206  
##  3rd Qu.:0.00000  
##  Max.   :1.00000  
##  NA's   :157
analysis.final.no.missing.dat <- na.omit(analysis.final.dat)
dim(analysis.final.no.missing.dat)
## [1] 2142  236
#1635

analysis.final.no.missing.dat[,row.names(met.data)] <- log(analysis.final.no.missing.dat[,row.names(met.data)])
write.csv(analysis.final.no.missing.dat, "analysis.final.no.missing.dat.batch5.csv")


out_dat <- c(); j <-0
for(i in row.names(met.data)){
   j <- j+1
   analysis.final.no.missing.dat$outcome <- analysis.final.no.missing.dat[,i]
   mod <- gee(outcome ~ delta.t+Age.e+Sex+Education+FC_DK+PC1+PC2+PC3+PC4+
                                 htn_meds+lipid_meds+nitro_meds+t2d_meds,
                     id = subject,
                      corstr = "exchangeable", data=analysis.final.no.missing.dat)

  coeff <- as.data.frame(summary(mod)$coeff)
  coeff$pval <- 2*(1-pnorm(abs(coeff[, "Robust z"])))
  out_dat <- rbind(out_dat, data.frame(metabolite = row.names(met.data)[j], 
                     time_eff = coeff["delta.t","Estimate"], 
                     time_sd = coeff["delta.t","Robust S.E."], 
                     time_pval = coeff["delta.t","pval"], 
                      Age_eff = coeff["Age.e","Estimate"], 
                     Age_sd = coeff["Age.e","Robust S.E."], 
                     Age_pval = coeff["Age.e","pval"], 
                        Male_eff = coeff["SexMale","Estimate"], 
                       Male_sd = coeff["SexMale","Robust S.E."], 
                       Male_pval = coeff["SexMale","pval"],
                     Educ_eff = coeff["Education","Estimate"], 
                     Educ_sd = coeff["Education","Robust S.E."], 
                     Educ_pval = coeff["Education","pval"],
                       FC.DK_eff = coeff["FC_DKTRUE","Estimate"], 
                       FC.DK_sd = coeff["FC_DKTRUE","Robust S.E."], 
                       FC.DK_pval = coeff["FC_DKTRUE","pval"],
                     PC1_pval = coeff["PC1","pval"], 
                     PC2_pval = coeff["PC2","pval"], 
                     PC3_pval = coeff["PC3","pval"], 
                     PC4_pval = coeff["PC4","pval"],
                       htn_med_eff = coeff["htn_meds","Estimate"], 
                       htn_med_pval = coeff["htn_meds","pval"],
                       lipid_med_eff = coeff["lipid_meds","Estimate"], 
                       lipid_med_pval = coeff["lipid_meds","pval"],
                      nitro_med_eff = coeff["nitro_meds","Estimate"], 
                      nitro_med_pval = coeff["nitro_meds","pval"],
                        t2d_med_eff = coeff["t2d_meds","Estimate"], 
                        t2d_med_pval = coeff["t2d_meds","pval"]))
}
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.733119087  0.009013721  0.003457100 -0.096737519 -0.008022164  0.172248455 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.914591456  0.776506021  0.200496374 -1.233367527  0.050233445  0.124572132 
##   nitro_meds     t2d_meds 
##  0.090918506  0.386914641
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.268273e+01 -2.468559e-02  8.604959e-03 -3.651780e-02  3.817791e-06 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -1.418635e-01 -1.422456e+00  2.087595e+00  2.662189e-02 -3.166560e+00 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  1.218771e-02  9.563366e-02  8.430542e-02  4.197985e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.069557161  0.008007251  0.007698846  0.071425507 -0.001941652  0.129717795 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.717146344 -0.340645578 -0.495349222 -0.490995691  0.021776528  0.053245183 
##   nitro_meds     t2d_meds 
##  0.064060307 -0.056254565
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.685832288  0.006469890  0.006874077  0.215943281 -0.003863832 -0.079589707 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.158419480  0.031819359  0.072119761 -0.180106748  0.007886937  0.021779916 
##   nitro_meds     t2d_meds 
##  0.066528758  0.027561649
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.2338048761 -0.0115929021  0.0054115939  0.0456037858 -0.0004170792 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0753911400  0.7101397382  0.5082425066 -1.5468120454  1.1933244836 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0452009575 -0.0114742320  0.0517068224 -0.1716907842
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.235125e+01 -2.414402e-03  6.849701e-05 -2.555362e-03  8.463992e-04 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  1.597916e-01 -8.691045e-03 -3.415860e-02 -1.467433e-01  4.784854e-01 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  7.420510e-03 -1.465237e-03 -1.607655e-02 -5.554370e-03
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.2413202191 -0.0006496512 -0.0005612039  0.0007840833 -0.0002933028 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0191890962 -0.1996178661  0.1537697622 -0.0855796611 -0.6699556426 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0065598667  0.0127246058 -0.0005198097 -0.0019404695
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 10.390982277 -0.014414199  0.018222178  0.206658104 -0.007349897  1.785154032 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  5.154849115 -5.711616896 -1.989710145  2.802558657 -0.023892840 -0.054724893 
##   nitro_meds     t2d_meds 
## -0.059254435  0.272226773
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.825810e+01  2.674230e-03  2.653620e-03  1.749028e-01 -4.786881e-05 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  7.410987e-02  4.760851e-01 -3.515536e-01  1.211644e-01  4.374623e-01 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  1.710292e-02  4.629250e-03  5.852433e-03 -2.510697e-03
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.674045042  0.002135185  0.011809643 -0.003991984  0.005188619 -0.022000040 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  4.692165131  2.185388534  0.810163890  1.471815412  0.118536455 -0.002177212 
##   nitro_meds     t2d_meds 
##  0.060548954 -0.035548535
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 11.128225800  0.007210991  0.003678823 -0.009873539  0.004101242 -0.003007953 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.295496491  0.268540311  0.249514334 -0.291820592 -0.022562364 -0.008856147 
##   nitro_meds     t2d_meds 
##  0.025973089  0.062556311
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.8051217252 -0.0022991818  0.0010836217  0.0215661912 -0.0002179875 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0324153252  0.2992615427 -0.0609614081 -0.3743490702 -0.0233407751 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0189863614  0.0064893855  0.0116503528 -0.0277490330
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.199788216 -0.001628424 -0.000226143 -0.006082547 -0.003688864  0.003913156 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.889665023 -0.227469534  0.028408813  0.924471802 -0.002127794  0.008343256 
##   nitro_meds     t2d_meds 
## -0.001943520  0.011562384
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.109666180  0.004117775 -0.007944410  0.025677982  0.012823704  0.735060808 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.313595532 -1.562396645 -4.622862254  2.450790646  0.190689467  0.025877057 
##   nitro_meds     t2d_meds 
##  0.024720317 -0.062024517
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.3804009885  0.0119727601  0.0054814247  0.0295251513 -0.0003188995 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1076127068 -0.3127424824 -0.2652046606  0.0615582921 -1.4267375369 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0625397929  0.0036903823  0.0538119162  0.0464438097
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.2252801915 -0.0042116450  0.0017255024 -0.0011592694 -0.0020937889 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.1078424684 -0.0337321237  0.0516067051 -0.2765531046  0.4332142967 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0077957490  0.0004718581 -0.0090428110 -0.0109312803
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.350707243  0.005818445  0.013090424  0.040859322  0.007977222 -0.353667378 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.113721852  0.975313314  0.358998519 -1.612997216  0.053623060  0.094250990 
##   nitro_meds     t2d_meds 
##  0.053566473  0.030117909
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
## (Intercept)     delta.t       Age.e     SexMale   Education   FC_DKTRUE 
## 11.74683146  0.01618432  0.01573028  0.04613133 -0.01162460 -0.20702367 
##         PC1         PC2         PC3         PC4    htn_meds  lipid_meds 
##  0.55893396 -1.15095697 -1.57078118  1.21007475  0.17738914  0.11455227 
##  nitro_meds    t2d_meds 
##  0.05206285  0.21733666
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.192847e+01 -7.132083e-06  2.492549e-04  5.169073e-02  7.814449e-03 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -1.338664e-01  3.535628e-01  1.530207e-01  3.951684e-01  6.419134e-02 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  1.892485e-02  1.269466e-02 -5.044690e-03  1.407807e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.701454266  0.001356990  0.009094404 -0.007569683  0.021153862  0.212490001 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  2.004907830  2.615364973  1.929285151 -2.186411261 -0.061237147  0.014087446 
##   nitro_meds     t2d_meds 
##  0.014622316 -0.177214350
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.861514729  0.013712878  0.006543266 -0.040948255 -0.015776061 -0.394082436 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.677051956  0.439783907 -1.531008293 -0.923181357  0.092370171  0.132518402 
##   nitro_meds     t2d_meds 
##  0.055134160  0.124706464
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##   8.070535413   0.004527536   0.014402043  -0.211083507   0.007764392 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  -0.227596207  -0.024988277  -2.786779488  -0.459741650 -11.366790861 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##   1.602429111   0.485259194  -0.199196251  -0.252585703
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.853664302  0.009919621  0.008321291 -0.081448340 -0.003031273 -0.062342924 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.544588407 -0.351909968 -0.658902255 -0.773979615  0.074231645  0.055046894 
##   nitro_meds     t2d_meds 
## -0.003831893  0.013214577
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 15.6752304086 -0.0000685656 -0.0015237658  0.0862933758  0.0034803677 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0997210984  0.3841497320 -0.1435866564 -0.8229410935  0.5041475286 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0058064391  0.0563324618  0.0125038053  0.0613185110
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.047157773  0.002366841  0.006039993  0.013347702 -0.009083265 -0.167996306 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.411688653  0.152865922  0.722115680 -0.729392951  0.014886032  0.063134771 
##   nitro_meds     t2d_meds 
##  0.052893512  0.096932490
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 16.961750459 -0.007638908 -0.005695468  0.085361200  0.002766344  0.079913185 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.173775580 -0.025436762 -0.158096225 -0.287075038  0.029453896  0.034711801 
##   nitro_meds     t2d_meds 
## -0.006363826 -0.023427370
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.5201579418  0.0088059228  0.0043451885  0.0438939244 -0.0001755126 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.3595441824 -0.8560603915 -0.8536613984 -1.4741133299 -0.3091524154 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0973761717  0.0828839301 -0.0387021485  0.3895163719
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.557241515  0.000816008  0.001714716  0.040965121  0.017675575  0.015504017 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.582928776  0.604267069 -0.111833328  0.551698242  0.062251631 -0.084589887 
##   nitro_meds     t2d_meds 
##  0.010617399  0.145976728
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.2458936368  0.0022036198  0.0051774223 -0.0040312248 -0.0051440988 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0460337272 -0.3574872098 -0.6286121534 -0.2511252680  0.4463214361 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0001188369  0.0104862894  0.0021278030 -0.0210705902
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 11.494450852  0.001950481 -0.002767252 -0.006305614  0.008289436 -0.072082751 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.332641871  0.349837401  0.220429393 -0.676520035 -0.023208203 -0.024281740 
##   nitro_meds     t2d_meds 
##  0.018393565  0.016513681
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 11.6557539904  0.0073048654  0.0032428872  0.1978533614 -0.0007558994 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0468209404  1.4617300685  0.1141243474  0.2559584179 -0.1360567774 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0723703865  0.0500258943  0.0041899615  0.0162718544
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.9589357407  0.0002236441  0.0007055517  0.2392565335 -0.0056073116 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1699605163  1.1056804533  0.3631431695  0.8405623744 -1.0231547363 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0001550094 -0.0064905386  0.0108911787  0.0262451685
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.3832190379 -0.0003115603  0.0007465360  0.0032518530  0.0001208505 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0069236975  0.0434148067 -0.2717028187 -0.4985378735  0.4613922153 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0057032467  0.0038175088 -0.0033647662 -0.0127015722
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
## (Intercept)     delta.t       Age.e     SexMale   Education   FC_DKTRUE 
##  9.84281312  0.01945159  0.01721697 -0.07856328  0.01497058 -0.10095088 
##         PC1         PC2         PC3         PC4    htn_meds  lipid_meds 
##  0.65652510  0.38936979  1.27554460 -1.61407811 -0.04294493 -0.08917559 
##  nitro_meds    t2d_meds 
##  0.10930568  0.15473104
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 11.164268495  0.013546223  0.005668468  0.050282582  0.004394027  0.458164860 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.834395679 -1.566535621 -1.815735481  1.451390728  0.077907881  0.037520611 
##   nitro_meds     t2d_meds 
## -0.002435733  0.385100954
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
##  9.455658933  0.008880587  0.009492466  0.197542045 -0.012539088 -0.302857111 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.469497167 -0.355275641  1.413790858  1.450128358 -0.073410990  0.193483582 
##   nitro_meds     t2d_meds 
##  0.244291870  0.272462169
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.797626045 -0.007221077 -0.006637522  0.081813476  0.003140186 -0.148133058 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.243887322  1.306108640  1.188704839 -0.965038743 -0.007632320  0.029698924 
##   nitro_meds     t2d_meds 
## -0.043328789  0.041769231
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.697343333  0.006653145  0.005510534  0.223513766 -0.002541356 -0.133682532 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.318404191  0.082998167  0.192145737 -0.186774832  0.011196071  0.017972316 
##   nitro_meds     t2d_meds 
##  0.064677049  0.022091868
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 11.8358061156 -0.0057847775  0.0024044072  0.0212583844  0.0018923494 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.2126775498  0.0435679022 -0.4673222761 -1.1068581016  0.5460185683 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0394387743  0.0008936793  0.0485276718 -0.1285963184
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.891198314 -0.020090634 -0.014141255  0.075219526  0.036060184 -0.578749308 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  3.439574905  2.156688046 -0.345281501 -0.823269963  0.040934443  0.042591835 
##   nitro_meds     t2d_meds 
## -0.059342925 -0.003958792
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  9.5178696547 -0.0000315193  0.0091676838  0.0925746355  0.0026601174 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1647426539  0.3169763905  0.2323853211  0.9495260288 -0.5605795092 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0628397595  0.1610212937  0.1349435138  0.1527060423
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.077128783  0.005338058  0.004521512  0.034032520  0.001707460  0.118402711 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.824036251  0.039469867  0.158179666  0.025151629  0.018997266 -0.005633106 
##   nitro_meds     t2d_meds 
##  0.011746748 -0.021752895
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.5881550286 -0.0000051936 -0.0035910008  0.0326604335  0.0055088793 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0106028588 -0.0169097612 -0.2778350570 -1.0841313441 -0.1629111903 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0192390516  0.0304886694 -0.0284719374  0.0864877722
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.197957555  0.018419566  0.021820905 -0.031570173  0.013639734  0.915402986 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  2.945128536 -0.940371687 -1.758235572  0.461581792  0.003838343  0.054011006 
##   nitro_meds     t2d_meds 
##  0.072813481  0.059445962
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.8651876759 -0.0030250883 -0.0009610439  0.0187112467 -0.0001788793 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0226181530  0.0711833142 -0.3272524426 -0.5890615554  0.5842414740 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0251619434  0.0549345285  0.0096856048  0.1283890511
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 17.3106537205 -0.0015705441 -0.0007030478  0.0847521842  0.0004152980 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0535168640  0.0132847794  0.3517551368  0.0953220638  0.2105827544 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0439826582  0.0161935815 -0.0163633795  0.0481814501
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 17.169610987  0.006588925  0.006306308 -0.045473557 -0.008814907 -0.234264704 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -2.219600520  0.151894063 -0.061694691 -1.570722792  0.020475340 -0.010033087 
##   nitro_meds     t2d_meds 
##  0.071747164  0.141267317
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.672873042 -0.006398564 -0.004781404  0.074937935  0.002489471  0.083153950 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.206148990 -0.061786983 -0.118166452 -0.084907958  0.024148113  0.029325267 
##   nitro_meds     t2d_meds 
## -0.004479405 -0.019608671
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.257786483 -0.005909925 -0.004446633  0.075161904  0.001350373  0.067860145 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.234764565  0.030002708  0.048796660 -0.323606130  0.021772634  0.028538593 
##   nitro_meds     t2d_meds 
##  0.003121296 -0.021054610
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
## (Intercept)     delta.t       Age.e     SexMale   Education   FC_DKTRUE 
## 10.06894841  0.01042554  0.01445491  0.06770575 -0.01007885 -0.02597488 
##         PC1         PC2         PC3         PC4    htn_meds  lipid_meds 
##  0.54294836 -0.40034014 -0.13650065 -0.18385104  0.03819566  0.03041061 
##  nitro_meds    t2d_meds 
##  0.05533896  0.01567844
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.674831622  0.003974051  0.004629492 -0.015506804  0.003092357 -0.066847697 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.753544299  0.888517191 -0.325706814 -0.882342809  0.094394833  0.081818899 
##   nitro_meds     t2d_meds 
##  0.018896326  0.128486616
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.1260259490  0.0058178226  0.0053027690  0.0702932575 -0.0033911774 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0985941254  0.4876966066  0.1232064013  1.1635652988 -1.1640628016 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0138075238 -0.0007158398  0.0676290709  0.0650699314
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 17.237380843 -0.001511678  0.001353690  0.070462221 -0.004845096  0.104072851 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.232853741 -0.153432393  0.032847137 -0.401824139  0.034716387  0.004229303 
##   nitro_meds     t2d_meds 
## -0.023592228  0.056803030
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.799214602  0.010124549  0.007442291 -0.083970467 -0.003628300  0.110347765 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.852506627 -0.704232272  0.045130565 -0.679889988  0.068546286  0.032367367 
##   nitro_meds     t2d_meds 
## -0.005483834 -0.029272976
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 17.660030021  0.002307127  0.000995006  0.056800248  0.002206485  0.031620285 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.121583206 -0.048022782 -0.215662593  0.351393871 -0.032209404  0.002706536 
##   nitro_meds     t2d_meds 
##  0.003985814 -0.018289932
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.328632e+01 -1.866332e-04  8.328449e-04  5.203290e-03  3.764728e-04 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  3.422191e-02  1.056394e-01 -2.572016e-01 -6.252200e-01  4.641403e-01 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -2.302828e-05  3.780853e-03 -4.856322e-03 -2.833622e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 15.1507324572 -0.0027530575 -0.0043450876  0.0742548529 -0.0005567243 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0153297567  0.3215348976  0.1200220149 -0.3677163038 -0.1953158497 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0463304885  0.0184670535 -0.0171184517  0.1032405323
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 10.7516282990  0.0001473342  0.0049012961  0.0650676437 -0.0042945111 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0281392305  0.0484969311  0.8242853939  0.3588964785 -0.2870871820 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0380322843 -0.0280272209  0.0464154234  0.0613040472
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.308245e+01 -4.286629e-03  8.050709e-04  1.998334e-02  8.713455e-05 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  3.120613e-02  3.606835e-01 -9.042838e-02 -7.041701e-01  1.272690e-01 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -2.248735e-02  5.597297e-06  1.465100e-02 -2.591296e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 10.805809520 -0.002007617  0.002533627 -0.035451168 -0.007017792 -0.122907736 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.717776291  0.617571106 -0.157560305  0.407297781 -0.014933861 -0.003951521 
##   nitro_meds     t2d_meds 
## -0.007026614 -0.044915616
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 10.322433134 -0.008180788  0.004660074  0.168133030  0.053207670 -0.018788204 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  9.145799564 -4.407054628  0.383476192  4.287145451 -0.077092617 -0.021466811 
##   nitro_meds     t2d_meds 
##  0.037108114  0.093553251
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.4644428469 -0.0020256094  0.0003185282  0.0158326406  0.0016752686 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0240111322  0.3304841730 -0.0652787978 -0.1241494670 -0.1272190229 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0059019739  0.0112848839 -0.0026589444 -0.0348525635
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.1473070106 -0.0025940348 -0.0041381576  0.0301089922 -0.0001293177 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0026229886  0.4692012828 -0.2669681836 -0.4414712562  0.5166813320 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0115904442  0.0816175690 -0.0101791071  0.0085267402
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 10.899861339  0.011281317  0.010171193 -0.005743257 -0.005743506 -0.078405303 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.693682314 -0.196178064 -1.046912947  0.471318275  0.043608982  0.040302667 
##   nitro_meds     t2d_meds 
##  0.061901415  0.124364484
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 18.355637329 -0.003490445 -0.002918177 -0.440813592 -0.004641658  0.005380106 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.128629467 -0.644620804  0.091508708 -0.479372393  0.062551127 -0.021219787 
##   nitro_meds     t2d_meds 
## -0.024394683  0.067364125
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 18.937685632 -0.002440377 -0.002007129  0.066872868 -0.002129488 -0.113378545 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.354321307  0.225954384 -0.585870450 -0.805273404  0.045907633  0.056867274 
##   nitro_meds     t2d_meds 
##  0.028539571  0.004067018
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
## (Intercept)     delta.t       Age.e     SexMale   Education   FC_DKTRUE 
## 16.08588017 -0.01097316 -0.02236515 -0.04881076  0.05186672 -2.26131559 
##         PC1         PC2         PC3         PC4    htn_meds  lipid_meds 
## -3.99681571  2.68045062 -0.56067021 -4.94093337 -0.09426860  0.10708458 
##  nitro_meds    t2d_meds 
##  0.05362262 -0.11316997
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.0663837809 -0.0009031501  0.0018856744  0.0100343036 -0.0060345684 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.1075097301  0.5749921013  0.1249374380 -0.1337650269  1.3040480158 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0118541227 -0.0141167919 -0.0166335100  0.0027189791
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.298510369  0.006622537  0.005174502 -0.066925126 -0.010710684 -0.096799289 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.289283164  0.032023593 -1.398010292 -0.098593489  0.081413623  0.139434549 
##   nitro_meds     t2d_meds 
##  0.009491769  0.064850671
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 15.9972040694  0.0021160076  0.0003552212 -0.0220321171 -0.0012539998 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0227874663 -0.2171023888 -0.5795667383  0.3150373426  0.6522449946 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0027003147 -0.0007067813 -0.0308588462  0.0170190900
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.813538166 -0.036617383 -0.001473997  0.325286466 -0.049784698  2.496460832 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -5.801998329 -5.572477159 -3.864902626  1.426953343  0.098295765  0.113328564 
##   nitro_meds     t2d_meds 
##  0.010003202  0.208581482
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.807861e+01  9.376259e-04 -3.510457e-05  8.762221e-02 -8.330959e-04 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  4.342230e-02  4.095014e-01 -1.409219e+00 -5.153244e-01  6.810570e-01 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  1.208967e-02  5.613719e-02  2.566902e-02  7.578618e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 17.8946408583  0.0003526078  0.0008693553 -0.0183051680 -0.0021827146 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1044583668 -0.3435936264 -0.2570954315  0.2111687711  0.6352509607 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0166490655 -0.0047118674 -0.0412849958 -0.0018956183
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.391109690 -0.063573698 -0.012010926  0.312742256 -0.040488244  3.049982591 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -7.908353047 -2.433796684 -3.043975708 -4.803308149  0.021138168  0.013617268 
##   nitro_meds     t2d_meds 
##  0.005449729  0.245230300
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.397751938 -0.024463757 -0.004818678  0.090051783  0.004774373  0.388101089 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.651177792 -0.074228678 -1.151956621  0.930084501 -0.008285825  0.010604454 
##   nitro_meds     t2d_meds 
## -0.024966256  0.017292463
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.547389625 -0.003006414 -0.002206790  0.131599661 -0.006205823 -0.012022724 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.280848810  0.068188909 -0.582601128 -0.808347143  0.087976556  0.042701111 
##   nitro_meds     t2d_meds 
##  0.014052328  0.184397884
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.302584593  0.007191477  0.005904462  0.018624536 -0.002575755 -0.056309773 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.426315937 -0.380713418 -0.013321773 -0.067048592  0.016370024  0.013846164 
##   nitro_meds     t2d_meds 
##  0.028548205  0.071702259
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.852090e+01  1.121466e-04  6.172806e-04 -1.650305e-03  8.384225e-05 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  2.667411e-02  1.700999e-01 -2.216640e-01 -5.306116e-01  2.760349e-01 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -5.224306e-03  1.512092e-03 -4.297666e-03 -1.842572e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.672478079  0.014033698  0.004225106  0.014844404  0.010082782 -0.331499584 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  2.226362111  0.762286775 -0.467051068  0.923530230  0.111844742  0.041958315 
##   nitro_meds     t2d_meds 
##  0.028335515  0.073988124
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 20.5275043869  0.0000624254  0.0004094289 -0.0021542925 -0.0003323003 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0043966677  0.0683002713 -0.2125303549 -0.4470506418  0.2342128860 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0036472957  0.0026136059 -0.0001982752 -0.0113298958
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.565796664  0.008376511  0.005852123  0.060138804  0.003566217 -0.066856479 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.562495464 -0.441730233 -0.450526298 -0.103445403  0.043199233  0.030352531 
##   nitro_meds     t2d_meds 
##  0.028985616 -0.011608752
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 17.0752700243 -0.0011017791 -0.0047762595  0.1766742667 -0.0030818727 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0094534669  0.7626974848  0.0581878382 -0.6008565700  0.1366782564 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0604536694  0.0327782755  0.0004630838  0.1790968089
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.951417522  0.002106161 -0.018001214  0.244355221  0.006341566  0.105667789 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  2.786561414 -5.061217025 -0.501946447  0.424917809  0.095759598  0.152207727 
##   nitro_meds     t2d_meds 
##  0.008920737 -0.072830027
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.176452583 -0.005889919 -0.011881343  0.109341402 -0.006649476 -0.498897469 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.424021618  0.111261232 -0.505196155  1.470811418  0.003414858  0.038700660 
##   nitro_meds     t2d_meds 
## -0.023329407  0.043168449
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.766586767 -0.002432804 -0.001006029  0.003451984  0.002189516  0.112455947 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.042260070 -0.823755701 -0.838638284  0.314504523  0.027299243  0.015725170 
##   nitro_meds     t2d_meds 
##  0.003464260  0.011878392
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
##  7.704913981  0.007810297  0.020919503  0.180753017 -0.012089980  0.252442435 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -4.114353780  1.249201382 -1.081424561 -0.610919564 -0.020720496 -0.012731530 
##   nitro_meds     t2d_meds 
##  0.021583004 -0.026289595
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.306142963 -0.001745557 -0.003057858  0.161431983 -0.001354064 -0.002019686 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.796052803 -0.579291618 -0.353994665  0.430477040 -0.022144201 -0.006389624 
##   nitro_meds     t2d_meds 
## -0.011702744 -0.141690603
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.4738381684  0.0031536584 -0.0024864590  0.0225618209  0.0009810741 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1449034038 -0.0189978808 -0.3562864690 -0.6664646822  0.3489868678 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0035933807  0.0376654766  0.0153586473 -0.0016131566
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 10.3863127896  0.0007725663  0.0031190496  0.2871038259  0.0063023306 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0319346257  1.9884172573  0.3761182440 -1.3657981355  1.6537609750 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0130874706  0.0290086061  0.0324810223 -0.0498687511
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.834647939 -0.011498313  0.005318438 -0.019421317 -0.006655469  0.346310139 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  3.465945927 -2.078581104 -2.215942837  4.681265393 -0.029704630  0.002455090 
##   nitro_meds     t2d_meds 
## -0.032644218 -0.113586850
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 17.737574851 -0.002391868 -0.005746108  0.126054327 -0.003016029  0.016508678 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.568966164 -0.126278038 -0.188811453  0.104879710  0.047296029  0.013374557 
##   nitro_meds     t2d_meds 
## -0.027692250  0.140257797
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.297357114  0.001208565 -0.009264038 -0.011865453  0.021126415  0.758924090 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.216513097  0.262724987 -3.216280147  2.031359151  0.164797959  0.050187213 
##   nitro_meds     t2d_meds 
## -0.022997925 -0.139771714
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
##  8.836976734  0.021398411  0.033501669  0.108564478 -0.023305916  0.107003033 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.435976379 -2.000048826 -1.310838476  1.310976271 -0.039681831  0.003218401 
##   nitro_meds     t2d_meds 
##  0.155127719  0.189072283
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.0316360371 -0.0249699816 -0.0010276531  0.1084093002  0.0004992806 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0765489916  3.2857386108 -0.4661756530 -1.9536149069 -0.1025179343 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0425788680  0.0043109443  0.0441368565 -0.1302998802
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.193151876  0.005776935  0.007741977  0.012917391 -0.003849510 -0.056082276 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.328598046  0.219009878  0.509885432  0.449740810 -0.022092229  0.031888979 
##   nitro_meds     t2d_meds 
##  0.037090195 -0.115504744
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.414075293  0.006687704 -0.001213167  0.168096184  0.005772377  0.131363457 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.476656236  0.085175959  0.257420725 -0.239322157  0.021470139 -0.020092685 
##   nitro_meds     t2d_meds 
##  0.041907178  0.036791198
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.818517389  0.001926891  0.014048954 -0.055781147  0.029056839 -0.410698788 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.295220817  2.765857207  1.504494551 -0.525405244 -0.022831249  0.026748864 
##   nitro_meds     t2d_meds 
##  0.020343346  0.106695272
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.583690741  0.009150737  0.006748784 -0.157914414  0.000656173 -0.096482086 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.937388735  0.503484524 -0.098974404 -1.799326059 -0.077453936 -0.082830465 
##   nitro_meds     t2d_meds 
## -0.012231786 -0.007242649
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.559866250  0.007268839  0.002152069 -0.006904652 -0.006063042  0.005881898 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.444302403 -0.222307197 -0.521878684 -0.424140653  0.040275547  0.065970630 
##   nitro_meds     t2d_meds 
##  0.010313249  0.105917115
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.442778e+01  2.244654e-04  7.004864e-05 -4.003773e-03 -2.036192e-04 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -9.092400e-02  4.931017e-01  2.443185e-01  3.401030e-02  4.943041e-01 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -6.741025e-03 -1.211049e-02 -1.415400e-02 -2.776429e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 17.7255870091  0.0024070194  0.0013737984 -0.0491352915 -0.0009827403 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0794435118 -0.4852033253 -0.2216275283 -0.2242098636  0.3885736530 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0013283578 -0.0195376383 -0.0036766869 -0.0339012077
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.659448134 -0.000180332 -0.005085725  0.053404495  0.004347661  0.150580610 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.253930281  1.517371081  0.895172758 -1.190999436 -0.031355712  0.018044838 
##   nitro_meds     t2d_meds 
##  0.034756392  0.019468193
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 18.572141016 -0.008453315 -0.004559487  0.030898939 -0.002366855 -0.442761471 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.132439916  0.493961980  0.772321369  0.341964325  0.021521378  0.008889102 
##   nitro_meds     t2d_meds 
##  0.019962905  0.024002319
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 15.7267051853  0.0005997602  0.0014185849 -0.0078929366  0.0004556454 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0171735089 -0.4811202196 -0.3017987861 -0.2393374167 -0.2089886993 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0045172103 -0.0149035440 -0.0081992462 -0.0136800192
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 11.892840801 -0.001342786  0.018177461  0.096613512  0.002784272  0.483547856 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.672138538 -1.498462627 -0.179344552  0.675686149  0.029496077 -0.006172630 
##   nitro_meds     t2d_meds 
##  0.019473610  0.257056748
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.999801511 -0.004088963  0.001888886 -0.112361241 -0.004331362 -0.362886406 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.947989045 -0.572085449 -0.039613793 -0.458926145 -0.002016553 -0.034423526 
##   nitro_meds     t2d_meds 
##  0.003011194  0.003922762
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.9949075107 -0.0122833225 -0.0060270368 -0.0157499067 -0.0002508356 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.5420605184 -0.3034874613  2.0245902171  1.2918787016 -1.1361760205 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0013484044 -0.0084913321 -0.0037026453  0.0873613119
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 11.669870781 -0.005666317 -0.002728270  0.003928235 -0.001501621 -0.126905160 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.227683812  1.248908584  2.399864446 -1.333882440  0.008439328 -0.031386305 
##   nitro_meds     t2d_meds 
##  0.049468188  0.050623189
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.2725581149 -0.0040675142 -0.0037513391  0.0499143985  0.0034238317 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1729336718  0.5755009505  0.6191953349  0.4360750629 -1.0317077710 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0386377874  0.0005229193 -0.0126686674  0.0773527280
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.607667350  0.002640840 -0.002688514  0.027767781  0.003353699 -0.006853819 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.167591554 -0.212806811 -0.602766058  0.571753981 -0.015871125  0.017263704 
##   nitro_meds     t2d_meds 
##  0.011054885  0.005187794
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 11.219252137  0.005325262  0.014483863  0.085473387 -0.002589814  0.169312806 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.118737917  0.203253867 -0.892965156 -0.932685742 -0.013980580 -0.014767701 
##   nitro_meds     t2d_meds 
##  0.105442570  0.163739221
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 18.680271679 -0.009960056 -0.007506960  0.220389699  0.007960016 -0.132345741 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.737354681  0.973591997  0.284624583 -0.706553902  0.051825038  0.014552187 
##   nitro_meds     t2d_meds 
## -0.012561759  0.133260578
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.241853304 -0.010950525 -0.005738808  0.368210434 -0.019368001 -1.614139189 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -2.614520039 -3.738346113 -2.865834854  3.002810691  0.130704736  0.104629784 
##   nitro_meds     t2d_meds 
##  0.027946786 -0.107472279
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 16.586399402  0.013628133  0.007115201  0.039088095  0.002383734  0.330614393 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.011486621 -0.988804659 -1.303109243 -0.015558048  0.058827161  0.037861688 
##   nitro_meds     t2d_meds 
## -0.002847411  0.376431656
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 16.794851518  0.002906584  0.001515940  0.052827228  0.007547556 -0.235503570 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  3.478117497 -2.098085857 -0.791622705  1.116433654  0.043267890 -0.014852533 
##   nitro_meds     t2d_meds 
## -0.028072374  0.285179536
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.6197654004 -0.0019863802 -0.0007809079 -0.0042966363  0.0049979430 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1761293576  0.7731843740  0.4583887464  0.1833976416  0.4080837528 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0074262762 -0.0098947991 -0.0016944911 -0.0128072881
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.433929595  0.002897596 -0.001427892 -0.006326853  0.001285215 -0.027114626 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.224059188  0.426385825  0.281252339  0.585897164  0.014470885  0.013906061 
##   nitro_meds     t2d_meds 
## -0.025287640 -0.003075893
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.6269863797  0.0004559694 -0.0030844247  0.0279485999  0.0003089077 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.3874165354 -0.1592989462  0.0998944824  0.2612812029 -0.8970767064 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0407256939  0.0407744011  0.0256619722  0.0524959685
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.1809111085 -0.0001639661 -0.0037005822 -0.0238389097 -0.0002496378 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0394842300 -0.2317347380 -0.4954639477 -0.5438355216 -0.0757709639 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0262257222  0.0275372211 -0.0099913251  0.0442229890
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.899445310 -0.006291441  0.007853501  0.010457052 -0.008127233  0.132811653 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.084224225 -0.062370654  0.162970765 -0.467482470  0.016249095  0.008306209 
##   nitro_meds     t2d_meds 
##  0.064029507  0.090264569
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 16.882673253 -0.006579015 -0.008230568  0.100800109 -0.005647232 -0.051286344 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.539832958 -0.025693505 -0.360278040  0.921447237  0.013397175  0.033350736 
##   nitro_meds     t2d_meds 
##  0.040125321 -0.270380671
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
## (Intercept)     delta.t       Age.e     SexMale   Education   FC_DKTRUE 
## 10.83951446  0.03320757  0.02073965  0.09537063  0.01385220  0.19318806 
##         PC1         PC2         PC3         PC4    htn_meds  lipid_meds 
##  2.40814135  0.13807663 -0.22315580  0.05814670  0.06509810  0.10572490 
##  nitro_meds    t2d_meds 
##  0.44949814  0.16189398
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.316956797 -0.002491751 -0.003374700 -0.056721072 -0.002931554 -0.352270752 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  2.000191416  0.668801117 -0.531552182  0.028070854  0.029508230  0.080174099 
##   nitro_meds     t2d_meds 
##  0.035425356  0.001081332
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.4094505858 -0.0028089498  0.0099183212  0.0951945988  0.0071704133 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.2361040821  0.6405955335 -1.2016231493  0.8956243229  0.3872815848 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0380989179  0.0009522764 -0.0264922335  0.0156411519
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.6626367230 -0.0041834637 -0.0005134659 -0.0837922937 -0.0050851620 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.5056039249 -1.4598341482 -0.4447120508  0.5154970882 -0.4899361376 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0034761060 -0.0209522686 -0.0090796872 -0.0204102117
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.163233346  0.027369661  0.011144708  0.270014282  0.005670108 -0.823188964 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  2.072584788  2.837791734  3.918340655 -4.213250934  0.211887052  0.538395678 
##   nitro_meds     t2d_meds 
##  0.061649137  0.280341920
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.6656737482 -0.0005256656  0.0004831619 -0.0042713024 -0.0037938134 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1154145440  0.0779019058 -0.3500818136  0.3078182142  0.7296050595 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0024109606 -0.0191618878 -0.0073004816  0.0342687110
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.674098945  0.005903669  0.003585387  0.068030076  0.004116737 -0.371265495 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.657282038  0.305845917  0.946623245 -1.526199667  0.117052322  0.149741637 
##   nitro_meds     t2d_meds 
##  0.018223173  0.211671027
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.284750459  0.007785889  0.008582620  0.085025643 -0.002844990 -0.149667191 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.526204962 -0.688481105  0.237770372 -0.459699202  0.042980644  0.025902588 
##   nitro_meds     t2d_meds 
##  0.034448176  0.087836467
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.3358065624 -0.0059339086 -0.0008388358 -0.0152483579  0.0162632273 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.9362128702 -0.0740373196  0.4701564924 -0.1005257771 -0.2288705169 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0509003227  0.0612034278  0.0691136926 -0.1128426719
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.885873070 -0.003207514 -0.000928357  0.052716585 -0.006777319 -0.220503493 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.228876279 -0.285566351  0.324755770 -0.130450406  0.041966685  0.051243188 
##   nitro_meds     t2d_meds 
##  0.028504892  0.042939160
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 10.110635285  0.001410142  0.007286849  0.062444288 -0.003439114  0.133767596 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.325075119 -0.943423396 -1.516978192 -0.419609883  0.039922354  0.061552590 
##   nitro_meds     t2d_meds 
##  0.019417624  0.020322779
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 16.436750360 -0.011847665 -0.000474324 -0.063899667 -0.002346166  0.281844610 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.974128711  0.296590964  0.242741980 -0.019503123 -0.003963232 -0.015314888 
##   nitro_meds     t2d_meds 
##  0.030733943 -0.022212538
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.352578979  0.010402696  0.004876116  0.043246472  0.027708471  0.388686827 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  3.407518453  1.270835276  0.746716154  0.796092903 -0.034624742 -0.079991168 
##   nitro_meds     t2d_meds 
##  0.019917283 -0.011728897
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.9730346567 -0.0005698244 -0.0010351903  0.0070661780  0.0042758070 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0074991289  0.1590992913 -0.2078347055 -0.4491927667  0.4875840258 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0186957147  0.0246284635 -0.0141073143 -0.0139704493
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 16.397085483  0.002695448 -0.003263484 -0.079088302  0.009257697 -1.318488397 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.537848290  1.313485072  2.860515306 -0.349991092 -0.016418903 -0.018974654 
##   nitro_meds     t2d_meds 
##  0.008589386 -0.091617120
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 18.463336601 -0.028950141 -0.034342213  0.376648426 -0.009950596  0.128963512 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.922760723 -3.174150858 -2.202732889  1.913198643  0.026175619 -0.176655379 
##   nitro_meds     t2d_meds 
## -0.041993080 -0.043010042
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.6722040021  0.0106595600  0.0023167197 -0.2445965645  0.0007705885 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1738593437 -0.9517496086  0.1051326505  0.4488674227 -0.7932353561 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0168855750 -0.0589333156  0.0114401954 -0.0236062383
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 10.403900686 -0.012879957 -0.008626914  0.061518160  0.010876397 -0.616334272 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.275007350 -1.807166418  0.879354628  0.939627547  0.980399886  0.064668416 
##   nitro_meds     t2d_meds 
## -0.257688471  0.050080875
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.4093163948  0.0047841965 -0.0007912307  0.0517602490 -0.0043469614 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1346616003 -1.4189651421  0.2717087061 -0.0885293555 -1.9321905122 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0583043129 -0.0229740415  0.0078710001  0.3025930116
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.566719776  0.019166573  0.019732864  0.129543308 -0.008840624  0.636520194 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.493351516  0.410889750 -1.223164718  0.105581394  0.165927518  0.037247917 
##   nitro_meds     t2d_meds 
## -0.086594034  0.019830424
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 11.6832231965  0.0009242744  0.0009232243 -0.0811922414  0.0130124787 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.2287764785  1.1275363897  0.5439647319 -0.0587305504  0.5548080541 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0244292903  0.0232771255  0.0191862244 -0.0462146489
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.208777097  0.006104257 -0.003616861 -0.060898764  0.013448482 -0.518266308 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.086585341  0.584938572 -0.009995869 -1.330051903  0.023407308  0.058522157 
##   nitro_meds     t2d_meds 
##  0.001388218 -0.069848854
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.8028733738  0.0012065696 -0.0002292434 -0.0196716969 -0.0005989771 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0891419051 -0.0449680627 -0.1539257476 -0.1192061965  0.8459346409 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0016114658 -0.0101052024  0.0022025539  0.0105606388
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 15.0557109177 -0.0025620933  0.0032620631  0.0716450151  0.0007529775 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0461905532 -0.0424593251  0.1709683035 -0.4997871774  0.3135353941 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0102206845 -0.0268389607  0.0081075250  0.0121967081
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.973860412  0.014616947  0.016514410 -0.088404898  0.005289611 -0.078088717 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -1.049924392  1.129220260  0.432490565  0.468924556 -0.052293164  0.041417776 
##   nitro_meds     t2d_meds 
##  0.071468473  0.037861934
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 19.060509182  0.002791811  0.002972270 -0.212481651 -0.002056926 -0.659814567 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -2.551815286  0.007943152  0.407334817 -1.556098529  0.031342986 -0.056547156 
##   nitro_meds     t2d_meds 
##  0.007922838  0.059874020
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.7114086824 -0.0065518344  0.0130363879 -0.0133834051  0.0981047462 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  1.6807620338  8.9129988627  2.3895054996  0.5571648171  1.5461758112 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0322314435  0.1728759056 -0.0003880965 -0.1500498621
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.157231412 -0.001012443 -0.007258209  0.187665306 -0.003249619  0.242607552 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.711458914 -0.182550634 -0.640375053  0.158928147  0.062092051 -0.030820953 
##   nitro_meds     t2d_meds 
## -0.009295757  0.127707166
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.761715138 -0.006748097 -0.004758479  0.087558918 -0.003895085 -0.024204285 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -1.501480679  0.098819924  0.312796611 -0.267707910  0.069506726  0.061445094 
##   nitro_meds     t2d_meds 
##  0.043655874  0.119100596
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.1274440920 -0.0007183214 -0.0039039076  0.0834457270  0.0055067884 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.5225289292  0.4662250869  0.1995350219  0.2065359935 -1.2223245673 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0047860536  0.0078492909  0.0389779119  0.1312462793
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.5809863082  0.0056928679  0.0052004215  0.0478958433  0.0036172247 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0779353338  0.4177455283 -0.0745920945 -0.5297392847  0.4657904980 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0005055282  0.0184121180  0.0207569954  0.0540955293
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 20.9941573380 -0.0007731194 -0.0003242943  0.0046803501  0.0012192605 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0288911347 -0.0389400311 -0.1990701435 -0.3654606160  0.3371084145 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0173625050  0.0137137183 -0.0124564010 -0.0184235086
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.3761978930  0.0021702906  0.0005490078  0.0019287475 -0.0019957092 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1140507148 -0.2129553545 -0.0142025246  0.0369904035  0.3379285813 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0036947980 -0.0152303100 -0.0095338457  0.0083701137
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 18.416418738  0.001326290  0.001171805  0.122678925 -0.001794347  0.035081842 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.031959435 -0.204621431 -0.725570433 -0.096484784  0.057013067  0.008268272 
##   nitro_meds     t2d_meds 
##  0.017756693  0.005832517
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.9507648141  0.0036870369 -0.0005237824 -0.0219848637 -0.0011229493 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.4021890776 -1.1208644438 -0.6822009681  1.1747324211 -0.4548034861 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0726470434 -0.0358146299 -0.0252138267 -0.0306515220
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.9334157282  0.0044332303  0.0029862166  0.0002012644  0.0173070567 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.1301795917  0.8701957214  0.3805327443 -0.8961449618 -0.2887620959 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0339472062  0.0333167912  0.0296692547 -0.0315156092
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 16.267570610  0.009455019  0.008872780  0.041656509  0.001028598  0.037916913 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.583958519 -0.358812044 -1.060561012  0.485183026  0.029569799  0.072100232 
##   nitro_meds     t2d_meds 
## -0.009775097  0.112270307
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.1021990722  0.0062293644  0.0054050269 -0.0087670308  0.0061450958 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0423455568 -0.1077757907  0.6652472982 -0.0547606034  0.2531875866 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0012283203  0.0002155707  0.0200862073  0.1016509478
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.952806955  0.006254681  0.008495188  0.238218712  0.013268262 -0.660733392 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.402527994  2.475338392  3.661506464 -2.927181379  0.194119325  0.474656749 
##   nitro_meds     t2d_meds 
##  0.084274433  0.133827552
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.034527559  0.009266462  0.008094931 -0.023545390  0.001279678 -0.068801192 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.030860629  0.882710403  0.093309011  0.462586652 -0.065170434  0.006848104 
##   nitro_meds     t2d_meds 
##  0.090863321  0.047083455
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.6525358369 -0.0009413305  0.0009355803 -0.0438632191 -0.0018380046 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1967307448 -0.2162184630  0.1140967206  0.7691812779  0.4995569408 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0060615275  0.0058194941 -0.0121865199  0.0196988325
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.059749194  0.001101333 -0.001606385 -0.098642671 -0.003847487  0.028948293 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -1.458441120 -0.477475789  0.042117209 -0.540847656  0.053869826  0.029733761 
##   nitro_meds     t2d_meds 
## -0.009670134  0.045844140
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.7779103887 -0.0134587038  0.0026652831  0.1196077827 -0.0004318594 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0492678878  2.2359938228 -0.6905908495 -1.2654297903 -0.6024614278 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0188325136  0.0034036162  0.0281214517 -0.0296454387
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.193516477  0.007490240  0.009763061 -0.182517187  0.008562206 -0.379230599 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.196367644  0.150326609 -0.205998507 -0.971094867  0.038400296  0.019891229 
##   nitro_meds     t2d_meds 
##  0.045937568  0.107074251
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.256191541  0.004144205  0.005588710  0.059661856  0.003547509  0.194640695 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.593084604  0.734515099  0.050506197 -0.512022928  0.032461243  0.043663121 
##   nitro_meds     t2d_meds 
##  0.020123742 -0.037354724
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.1143264355 -0.0030868123  0.0005741783  0.0566552911 -0.0004349666 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.3001629928 -0.3433605116  0.5934319964  0.2553150637 -0.7600443238 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0035894571 -0.0187098347  0.0477628858  0.1473251558
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.352224e+01  4.462092e-03 -4.478713e-05  9.544383e-03  9.636447e-03 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  5.575206e-01  1.707856e+00  6.289462e-01 -4.117327e-01  1.144587e+00 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  2.302439e-02 -5.856379e-03  2.428501e-02 -1.501646e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 11.624690839  0.009538450  0.004660518  0.136683960 -0.008686146  0.856343475 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.423931673 -0.948347438  0.057561685  2.349410846 -0.032898927 -0.045550429 
##   nitro_meds     t2d_meds 
##  0.009027933  0.071391523
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 11.746747826  0.007048568  0.007619296 -0.007679605 -0.007799414  0.048439312 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.422314355 -0.341160060 -0.030814592  0.509444366  0.028602377 -0.048203910 
##   nitro_meds     t2d_meds 
##  0.018471489  0.036746052
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
## (Intercept)     delta.t       Age.e     SexMale   Education   FC_DKTRUE 
## 13.61126404  0.01816403  0.01997182  0.03649806  0.03161903  0.98614401 
##         PC1         PC2         PC3         PC4    htn_meds  lipid_meds 
##  2.69748872  2.22025958  2.52700721 -0.73918851 -0.07346482 -0.08149553 
##  nitro_meds    t2d_meds 
##  0.02601996  0.01929496
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 11.9280337482  0.0040034671  0.0063871859  0.1942126396 -0.0073511020 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0712266017  0.3747793257 -0.6333121214 -0.2345191231  0.3321461350 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0319887865 -0.0009141139  0.0667632590  0.0393668083
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.2900835848 -0.0058159722  0.0001309569 -0.0388372990  0.0010041687 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1140671882  0.5513291185 -0.0454748169  0.0368514332  0.2717989246 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0078119449 -0.0067547833  0.0206463427 -0.0428361033
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.945926e+01  5.774490e-03  3.782505e-03 -2.135446e-01  7.693365e-06 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -7.074380e-02 -2.791462e+00 -3.281029e-01  4.501348e-01 -1.682230e+00 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  3.342087e-02 -2.753862e-02 -8.283499e-03  7.221452e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.697502474  0.005636143  0.012663609 -0.052989097 -0.001224681 -0.096493205 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.371522407 -0.211784330  0.334965882 -0.875079722  0.020332608 -0.012912799 
##   nitro_meds     t2d_meds 
##  0.050896677  0.245401397
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 10.328109122 -0.006259570  0.006036890  0.144318563 -0.005867261  0.310918954 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -1.549968382 -0.801805907  0.918393458  0.615085426 -0.000057604 -0.033440249 
##   nitro_meds     t2d_meds 
## -0.009754977  0.065820721
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.4177920307  0.0077793797  0.0036226347 -0.0141256764 -0.0003924469 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.2399716815 -0.3125501610  0.3164649065 -0.0842526262 -0.8317088707 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0064688975 -0.0031124423  0.0354434713  0.1716240326
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.1474358289 -0.0004632423  0.0011027313 -0.0085428827  0.0033087029 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0017848706 -0.5098146045 -0.4563452189 -0.6224989055 -0.1307030958 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0106277706 -0.0062191066 -0.0183725991 -0.0225526043
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.041036890 -0.002181489 -0.007676067  0.280724560 -0.002961213  0.186084917 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.602131149 -1.276633157 -0.935026738  0.235169972 -0.009758134 -0.045096887 
##   nitro_meds     t2d_meds 
## -0.016130561 -0.001126237
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
## (Intercept)     delta.t       Age.e     SexMale   Education   FC_DKTRUE 
## 13.65721324  0.01307704  0.01166384 -0.09674429  0.03295863 -0.06759773 
##         PC1         PC2         PC3         PC4    htn_meds  lipid_meds 
## -0.48038781  0.27624933  0.42512363  1.40723767  0.01330593 -0.05431784 
##  nitro_meds    t2d_meds 
##  0.02224398  0.01583034
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.202966989  0.009279404  0.012565806  0.012195809 -0.007259825 -0.062047603 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.138307626 -0.737567521  0.183206535  0.210855867  0.029959088  0.024153252 
##   nitro_meds     t2d_meds 
##  0.066323996  0.125327019
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.996417161  0.011911383  0.006264757 -0.074416594  0.016528330  0.260001748 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.009339512  1.547626946 -1.087184401  1.627919450 -0.046889846 -0.023831385 
##   nitro_meds     t2d_meds 
##  0.061599330  0.063344755
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.0140662149  0.0029031971  0.0029814151  0.0039166159  0.0009723594 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0596771817 -0.2261321619 -0.3041879829 -0.0391019313 -0.4906638355 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0048887760  0.0057926350 -0.0073729071  0.0232819462
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.523707871 -0.004735796 -0.000352444  0.000564320  0.002769619  0.117074625 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.955857360 -1.047598837 -0.693995747  1.001662197 -0.010830785  0.014722319 
##   nitro_meds     t2d_meds 
## -0.006225074 -0.043689219
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.328797e+01 -8.676715e-03 -3.462155e-03  6.597449e-02 -7.446616e-03 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -2.041669e-01 -5.714783e-02 -6.392473e-01 -5.352166e-01  1.170820e+00 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  9.634408e-03 -6.570631e-05 -1.306754e-02 -2.528314e-03
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 11.6714805918  0.0140166813  0.0130180781  0.0016727454  0.0021223563 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0701156656  0.7946839090 -0.6112704166  0.1351756545  0.0266016345 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0143954959  0.0008657391  0.0886906608  0.1594761715
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.278680842  0.027497165  0.005228477 -0.079815887  0.020094956  0.511670828 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  3.613012533 -0.212691704 -0.591586229 -1.686653961 -0.030235402  0.044568535 
##   nitro_meds     t2d_meds 
##  0.038449042 -0.035916919
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.352258553 -0.011951240  0.002860219  0.066692913  0.001561498 -0.161063835 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.884378170  2.134166961 -3.681039016 -0.031681599 -0.066768079 -0.027736734 
##   nitro_meds     t2d_meds 
##  0.105856652 -0.167645051
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.742074182  0.014965754  0.001688377  0.134636494  0.028426229 -0.046940459 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.469803752 -0.122551456 -0.749353280  0.092689381 -0.005658647  0.020121290 
##   nitro_meds     t2d_meds 
## -0.004457891 -0.088855545
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.226741626  0.016475809  0.013333920  0.083091454  0.002074383 -0.052499748 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.800970744 -0.200005576  0.266002808 -0.342151494 -0.020906307  0.002662944 
##   nitro_meds     t2d_meds 
##  0.078011253  0.081998478
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.998700902 -0.002213916 -0.003212911 -0.014874248 -0.001966807 -0.086124526 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.863593837  0.093900171 -0.548198179  1.731268674  0.010599222 -0.007984298 
##   nitro_meds     t2d_meds 
##  0.021981140 -0.027082529
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 16.3945195494  0.0010634905  0.0010609345 -0.0132754512 -0.0006455213 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0191429294 -0.2666628698 -0.0844124774 -0.2021458080  0.3132946926 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0015289167 -0.0071074750 -0.0077170204 -0.0313370121
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 13.459279696 -0.004829474 -0.001168242  0.022744114  0.004733817  0.043817637 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.920702718 -0.255490399 -0.809072297 -0.186718041 -0.009919005 -0.006836616 
##   nitro_meds     t2d_meds 
##  0.005178948 -0.002238515
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 18.227418257 -0.008751412 -0.002654281  0.100925904 -0.002801980 -0.440934688 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -1.040681503  0.896901027  0.628020333 -0.670503403  0.015239619  0.002620504 
##   nitro_meds     t2d_meds 
##  0.006289558 -0.065048528
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 11.4125836841 -0.0019894009  0.0009529088  0.0176094640  0.0007417648 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0425839905  0.5904309214  0.2309663385  0.4549907241  0.3577654796 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0012362731 -0.0157938457 -0.0085646960  0.0006889556
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 14.308007198  0.026390555  0.022424919 -0.113854429 -0.003774761  0.124758141 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.489979464  0.932964964 -0.864400282 -0.679580201 -0.062349800  0.046485208 
##   nitro_meds     t2d_meds 
##  0.067282450  0.195133858
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.8406977074  0.0068575593  0.0027539919  0.0508698759 -0.0061466823 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.1207813116 -1.6388712284  0.2020155755  0.1191210782 -1.7459066282 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0284511053 -0.0516668854 -0.0009601813  0.2580646067
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
## (Intercept)     delta.t       Age.e     SexMale   Education   FC_DKTRUE 
## 13.60471596  0.01034998  0.00247420 -0.02809258  0.01481661  0.60367050 
##         PC1         PC2         PC3         PC4    htn_meds  lipid_meds 
##  1.47361282  0.83550200 -1.24079106  1.35941859  0.09484509  0.03590414 
##  nitro_meds    t2d_meds 
##  0.02214967 -0.01864003
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.772645989  0.004898189  0.010488072  0.032564543  0.004455523  0.198500916 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.635019940  0.096153356  0.893508173 -0.194180980  0.001026741 -0.013178607 
##   nitro_meds     t2d_meds 
##  0.054230279 -0.018976276
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.072848109 -0.003488888 -0.002585792 -0.006888433 -0.002002579  0.040787922 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  1.675153234 -0.342142871 -1.113580804  1.445248944  0.011093487  0.014348577 
##   nitro_meds     t2d_meds 
##  0.022410620 -0.028108290
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.1995930168 -0.0044488170 -0.0028013889  0.0008977923 -0.0029324310 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0725516130  0.2448268981 -0.3677852926 -0.2421984487 -0.1121141619 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0388276549  0.0041513538 -0.0052426661 -0.0365518278
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.3261103949  0.0084314547  0.0028934482 -0.0123727993  0.0015545669 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0001321374  0.6989594594  0.3050779539  0.0720371792 -0.9989352287 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0229612064 -0.0051733253  0.0538601926 -0.0068718942
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 13.2607805524 -0.0002836392  0.0036684643  0.0009995075  0.0017762315 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0376832712  0.5109119354 -0.0968473521 -0.2911383966  0.2708530941 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -0.0148083297  0.0087901455  0.0074907931  0.0107018865
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 19.504173353 -0.008500535 -0.003571552  0.045581002 -0.009045207 -0.481479879 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.265514830  0.674495493  1.244714706  0.247548760  0.033933019 -0.002933456 
##   nitro_meds     t2d_meds 
##  0.022189449  0.021150017
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 15.6024061978 -0.1379932502  0.0010047251  0.0194038432  0.0076545992 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.6552141074  0.8650791350 -1.6276210867 -0.2490175185 -0.0001662132 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0485700212  0.1683352733 -0.0140805569 -0.0708872479
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.048221511 -0.005199502 -0.003808401  0.166665169 -0.004322494 -0.026454570 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
##  0.700200358 -0.094006443 -0.469767258 -0.065444190  0.035021819 -0.001711970 
##   nitro_meds     t2d_meds 
## -0.008726316  0.100954698
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 16.283079904  0.014600851  0.005254195  0.022858045  0.004449699  0.567170510 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.321898478 -0.386561842 -2.166931640  1.610242839  0.107165722  0.072354080 
##   nitro_meds     t2d_meds 
## -0.056888575  0.454904087
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 12.8809133930  0.0018158905  0.0061984660 -0.2652743779 -0.0145260809 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.4006493136 -0.7218787375 -0.7414381499 -0.6150688869  0.4026462893 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0327199776  0.0009560413  0.0183240031  0.1154776957
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.3919241546  0.0003848655  0.0004158978 -0.0171626554 -0.0004613894 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -0.0825654134 -0.3853300427  0.0526024667  0.0628773905  0.1626343214 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0010250827 -0.0180217143 -0.0057099345 -0.0006638781
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 20.4631588896  0.0004078203  0.0003804524 -0.0096315253 -0.0005303364 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0320078990 -0.3189441922 -0.1693456813 -0.2923186433  0.2617862350 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0110466826  0.0027481221 -0.0042065277 -0.0204303884
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 11.350417095  0.009415358 -0.010935374 -0.178557688 -0.004191069 -0.785984772 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -1.653636529 -3.299238878  4.369810436 -4.760729603 -0.078701934  0.122486077 
##   nitro_meds     t2d_meds 
##  0.278840908  0.604293363
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 17.870975045  0.005257604  0.003015923 -0.002878465 -0.002424840 -0.104041388 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.170912526  0.450142492  0.400845174 -0.901894697 -0.004794941 -0.017338254 
##   nitro_meds     t2d_meds 
##  0.010987666  0.115632848
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.452091e+01 -2.886010e-03 -6.710236e-05  1.387576e-02  5.989235e-04 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -2.508443e-03  7.978785e-02  3.619866e-01 -1.069625e-01  3.104745e-01 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -2.995198e-02  1.653328e-02  9.215364e-03  3.742656e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 16.580376347 -0.002806289 -0.004344457  0.038620189  0.004285286 -0.054664693 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.246222633 -0.752447573 -0.589043903  0.648843498  0.006130561 -0.001682803 
##   nitro_meds     t2d_meds 
## -0.014960653  0.046020914
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
## 14.5604466680 -0.0053401653 -0.0010078645 -0.3959965940 -0.0050254202 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
##  0.0080765157  1.0305414528 -0.6383909403  0.0009346226  0.1079505417 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
##  0.0880454246  0.0065926570 -0.0270261305  0.0808102886
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
## (Intercept)     delta.t       Age.e     SexMale   Education   FC_DKTRUE 
## 11.98220835  0.00819838  0.01020543 -0.02343024  0.01958597 -0.01571246 
##         PC1         PC2         PC3         PC4    htn_meds  lipid_meds 
##  1.14322802  1.31300833  0.30818410 -1.02386045  0.00658681 -0.04839958 
##  nitro_meds    t2d_meds 
##  0.04370292  0.04929267
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 15.140984318  0.013389248  0.005240920  0.125612418 -0.021940894 -0.220015729 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.740191637 -0.499664495 -0.122965332  1.187985182  0.142022161 -0.106206661 
##   nitro_meds     t2d_meds 
##  0.004290152  0.214685216
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.686345060  0.002138627 -0.020802364 -0.007205768  0.029667219 -0.558579057 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.191806659  0.975063267  0.209953365 -2.649007529  0.007587507  0.025712863 
##   nitro_meds     t2d_meds 
## -0.017538549  0.255578154
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##   (Intercept)       delta.t         Age.e       SexMale     Education 
##  1.370377e+01  8.830158e-03  4.826548e-03 -6.604402e-03  9.659358e-05 
##     FC_DKTRUE           PC1           PC2           PC3           PC4 
## -6.125754e-02  4.800594e-01 -3.942969e-01 -6.371963e-01 -2.765378e-01 
##      htn_meds    lipid_meds    nitro_meds      t2d_meds 
## -2.947329e-02 -4.390119e-03  3.529447e-02 -4.866873e-02
## Beginning Cgee S-function, @(#) geeformula.q 4.13 98/01/27
## running glm to get initial regression estimate
##  (Intercept)      delta.t        Age.e      SexMale    Education    FC_DKTRUE 
## 12.711109325  0.008225954  0.003195425  0.142688194 -0.008390450 -0.079409235 
##          PC1          PC2          PC3          PC4     htn_meds   lipid_meds 
## -0.255295437  0.892419943 -0.328648024  0.068159506  0.081275342 -0.106706163 
##   nitro_meds     t2d_meds 
## -0.013938767  0.158049394
time_pval_adj <-  p.adjust(out_dat$time_pval, method="BH")
out_dat1 <- add_column(out_dat, time_pval_adj, .after = 2)
out_dat2 <- out_dat1[order(out_dat1$time_pval), ]

out_dat3 <- left_join(metab.look.up.table, out_dat2, by=c("fake.metab.names" = "metabolite")) %>%
  mutate(metabolite = orig.metab.names)
  out_dat3 <- out_dat3[order(out_dat3$time_pval), ]
  
write.csv(out_dat3, "Age_rel.change.assoc_batch5.pc_gee.06.22.2024.csv", row.names=F)

#Annotation

annot.dat <- read.csv(paste0(annot.dir, "llfs.annotation.03.30.2023.csv")) %>%
  mutate(Compound.Name = Input.name)

sum(out_dat3$metabolite %in% annot.dat$Compound.Name)
## [1] 220
#188

out_dat1_annot <- data.frame(annot.dat, out_dat3[match(annot.dat$Compound.Name, out_dat3$metabolite),])
out_dat1_annot <- out_dat1_annot[order(out_dat1_annot$Age_pval), ]

write.csv(out_dat1_annot, "annotated_Age_rel.change_assoc_batch5.pc_gee.06.22.2024.csv")

Plot

metab <- as.character(out_dat3$fake.metab.names[1:100])
true.name <- as.character(out_dat3$metabolite[1:100])
for(i in 1:30){
   plot.data  <- analysis.final.no.missing.dat %>%
     select( c("subject", metab=metab[i], "Age.e", "delta.t","visitcode")) %>%
       mutate( Age.p = Age.e+delta.t)
       
    png(paste0("plot_dir/",true.name[i], "_lines.png"))
  print(ggplot(plot.data, aes(x=Age.p, y=metab, group=subject)) + 
          geom_line() +
          theme_bw() +
          ylab(paste0("Age", true.name[i])))
  dev.off()

}

#Plot for paper

analysis.final.no.missing.dat <- read.csv("analysis.final.no.missing.dat.batch5.csv", header=T)
 
plot(analysis.final.no.missing.dat$Age.e, analysis.final.no.missing.dat$metab53)

# llfs.data.batch5.phen <- data.frame(llfs.data.batch5, 
                                  #  analysis.final.no.missing.dat$metab53[match(llfs.data.batch5$subject,
                                    #                                            analysis.final.no.missing.dat$subject)])
#write.csv(llfs.data.batch5.phen,"bad_phenylalanin.csv", row.names=F)
   
kynurenine <- analysis.final.no.missing.dat$metab81
tryptophan <- analysis.final.no.missing.dat$metab26
tryptophan.betaine <- analysis.final.no.missing.dat$metab67
N.ACETYLTRYPTOPHAN <- analysis.final.no.missing.dat$metab11
Ergothioneine <- analysis.final.no.missing.dat$metab40
Tartaric.Acid <- analysis.final.no.missing.dat$metab105
Melatonin <- analysis.final.no.missing.dat$metab62
Gamma.Linolenic.Acid <- analysis.final.no.missing.dat$metab138
Cortisol <- analysis.final.no.missing.dat$metab6
Creatine <- analysis.final.no.missing.dat$metab9
Warfarin <- analysis.final.no.missing.dat$metab86
Seven.Hydroxy.3.Methylflavone <- analysis.final.no.missing.dat$metab218
Acesulfame <- analysis.final.no.missing.dat$metab211
Glucose <-  analysis.final.no.missing.dat$metab207
Norvaline <- analysis.final.no.missing.dat$metab5
 Glycocholic <- analysis.final.no.missing.dat$metab220
 N.ACETYLSEROTONIN <- analysis.final.no.missing.dat$metab12
 urate <- analysis.final.no.missing.dat$metab155
 
plot.data  <- analysis.final.no.missing.dat %>%
     select( c("subject", "Age.e", "delta.t","visitcode")) %>%
       mutate( Age.p = Age.e+delta.t)
 data.plot <- data.frame(plot.data, 
                        kynurenine, tryptophan, tryptophan.betaine, N.ACETYLTRYPTOPHAN, Ergothioneine, Tartaric.Acid, Melatonin,
                        Gamma.Linolenic.Acid, Cortisol, Creatine, Warfarin, Seven.Hydroxy.3.Methylflavone, Acesulfame, Glucose,
                        Norvaline, Glycocholic,N.ACETYLSEROTONIN, urate )  

   for(i in 6:23){

   p<- ggplot2::ggplot(data=data.plot, aes(x=Age.p, y=data.plot%>% pull(i), group=subject))+
    geom_line(size=1) +
          theme_bw() +
             xlab("Age")+ylab(names(data.plot)[i])+
 theme(axis.text.x = element_text(face="bold", color="#993333", 
                           size=25, angle=0, vjust = 0.25, hjust=+0.5),
           axis.text.y = element_text(face="bold", color="#993333", 
                           size=25, angle=0, vjust = 0.25, hjust=-1.0),
                   text = element_text(family = "Arial", size=25))
   print(p)
  }
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## i Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.